Guided Diffusion for the Discovery of New Superconductors
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909814909566976 |
|---|---|
| author | Prakash, Pawan Gibson, Jason B. Li, Zhongwei Di Gianluca, Gabriele Esquivel, Juan Fuemmeler, Eric Geisler, Benjamin Kim, Jung Soo Roitberg, Adrian Tadmor, Ellad B. Liu, Mingjie Martiniani, Stefano Stewart, Gregory R. Hamlin, James J. Hirschfeld, Peter J. Hennig, Richard G. |
| author_facet | Prakash, Pawan Gibson, Jason B. Li, Zhongwei Di Gianluca, Gabriele Esquivel, Juan Fuemmeler, Eric Geisler, Benjamin Kim, Jung Soo Roitberg, Adrian Tadmor, Ellad B. Liu, Mingjie Martiniani, Stefano Stewart, Gregory R. Hamlin, James J. Hirschfeld, Peter J. Hennig, Richard G. |
| contents | The inverse design of materials with specific desired properties, such as high-temperature superconductivity, represents a formidable challenge in materials science due to the vastness of chemical and structural space. We present a guided diffusion framework to accelerate the discovery of novel superconductors. A DiffCSP foundation model is pretrained on the Alexandria Database and fine-tuned on 7,183 superconductors with first principles derived labels. Employing classifier-free guidance, we sample 200,000 structures, which lead to 34,027 unique candidates. A multistage screening process that combines machine learning and density functional theory (DFT) calculations to assess stability and electronic properties, identifies 773 candidates with DFT-calculated $T_\mathrm{c}>5$ K. Notably, our generative model demonstrates effective property-driven design. Our computational findings were validated against experimental synthesis and characterization performed as part of this work, which highlighted challenges in sparsely charted chemistries. This end-to-end workflow accelerates superconductor discovery while underscoring the challenge of predicting and synthesizing experimentally realizable materials. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25186 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Guided Diffusion for the Discovery of New Superconductors Prakash, Pawan Gibson, Jason B. Li, Zhongwei Di Gianluca, Gabriele Esquivel, Juan Fuemmeler, Eric Geisler, Benjamin Kim, Jung Soo Roitberg, Adrian Tadmor, Ellad B. Liu, Mingjie Martiniani, Stefano Stewart, Gregory R. Hamlin, James J. Hirschfeld, Peter J. Hennig, Richard G. Superconductivity Materials Science Artificial Intelligence The inverse design of materials with specific desired properties, such as high-temperature superconductivity, represents a formidable challenge in materials science due to the vastness of chemical and structural space. We present a guided diffusion framework to accelerate the discovery of novel superconductors. A DiffCSP foundation model is pretrained on the Alexandria Database and fine-tuned on 7,183 superconductors with first principles derived labels. Employing classifier-free guidance, we sample 200,000 structures, which lead to 34,027 unique candidates. A multistage screening process that combines machine learning and density functional theory (DFT) calculations to assess stability and electronic properties, identifies 773 candidates with DFT-calculated $T_\mathrm{c}>5$ K. Notably, our generative model demonstrates effective property-driven design. Our computational findings were validated against experimental synthesis and characterization performed as part of this work, which highlighted challenges in sparsely charted chemistries. This end-to-end workflow accelerates superconductor discovery while underscoring the challenge of predicting and synthesizing experimentally realizable materials. |
| title | Guided Diffusion for the Discovery of New Superconductors |
| topic | Superconductivity Materials Science Artificial Intelligence |
| url | https://arxiv.org/abs/2509.25186 |